TEAM 1: FeedBridge
Project Mentor:
Meera Sankar, MD, Department of Pediatrics, Division of Neonatal and Developmental Medicine, Stanford.
Project Summary
Physiologic poor feeding in newborns, leading to poor weight gain, jaundice, and hospital readmissions, is a significant public health concern. FeedBridge aims to provide personalized, data-driven guidance to parents and physicians, enabling timely intervention and improved newborn outcomes. The application will be co-designed, tested, and potentially funded for a pilot study at Lucile Packard Children’s Hospital Stanford and its outpatient clinics.
TEAM 2: NeutroFeverGuard
Project Mentors:
*Johannes Jung, MD, PhD, Department of Hematology and Oncology, Technical University of Munich.
Thomas Kaar, TUM Graduate Student
Simon Dosch, TUM Graduate Student*
Project Summary
This project addresses the urgent need for early detection of febrile neutropenia in chemotherapy patients by developing a real-time monitoring app using wearable technology, specifically the Apple Watch. Febrile neutropenia is a serious complication of chemotherapy, characterized by the onset of fever in patients with low white blood cell counts (specifically neutrophils) as a result of chemotherapy-induced immunosuppression. It is considered a medical emergency because the weakened immune system leaves patients highly vulnerable to life-threatening infections.The proposed app continuously tracks body temperature, heart rate and oxygen saturation, issuing immediate alerts if a predefined temperature threshold is exceeded. This early warning system encourages patients to seek prompt medical attention, reducing delays in antibiotic administration and mitigating risks of severe complications. Additionally, the app stores comprehensive heart rate, oxygen saturation and temperature data, providing healthcare providers with valuable insights for enhanced monitoring, timely intervention, and improved patient outcomes. This innovation aims to decrease hospital admissions, lower healthcare costs, and improve the safety and quality of care for vulnerable patients.
TEAM 3: Stanford 360 Childhood Obesity Treatment App
Project Mentors:
Janey S.A. Pratt, MD, FACS, Clinical Professor, Department of Surgery - Pediatric Surgery, Stanford University School of Medicine.
Daryl DeGuzman, RN, Pediatric General Surgery, Lucile Packard Children's Hospital Stanford.
Gillian Fell, MD, Clinical Instructor, Department of Surgery - Pediatric Surgery, Stanford University School of Medicine.
Project Summary
Severe childhood obesity is on the rise globally. The American Academy of Pediatrics recommends metabolic and bariatric surgery (MBS) as the safest and most effective treatment for affected children, best provided by a multidisciplinary team of dieticians, nurses, psychologists, pediatricians, and surgeons. At Lucile Packard Children’s Hospital, our high-volume pediatric bariatric surgery program (#4 nationally) treats over 50 patients annually, with nearly 120 enrolled at any time. To enhance our program, we propose developing a pediatric-specific app to track lifestyle changes before and after surgery. Unlike existing weight-loss apps like NOOM, Simple, and Reverse Health, our app will not emphasize weight tracking and will instead align with our “60-60-60 rule”: 60 oz of water, 60 grams of protein, and 60 minutes of physical activity daily. The app will allow patients to log meals with photos, track physical activity automatically, and record fluid intake, providing positive feedback for meeting goals. This tool aims to improve compliance with the 60-60-60 rule, support long-term lifestyle changes, and enhance weight loss outcomes and quality of life for our patients.
TEAM 4: QuanBioSync
Project Mentor: Astrid Androsch, CEO & Co-Founder, QuanBio.com
Project Summary
Cardiovascular disease (CVD) typically develops over many years but is often detected only in its later stages. Early detection and continuous patient monitoring are crucial for enabling precision medicine and personalized treatment.
CVD remains the leading cause of death worldwide, with current diagnostic tools often inaccessible due to their cost and complexity. Our project proposes a mobile app, QBS, designed to address this issue by providing a remote monitoring extension of QuanBio’s affordable, non-invasive solution for early detection and monitoring of CVD. Our current approach delivers predictive assessments that enable earlier, more effective interventions using state-of-the-art machine learning and robust statistical methods. Built on the Stanford Spezi framework for iOS and compatible with devices like Apple Watch and QuanCardio, QBS will use real-time Photoplethysmography (PPG) data to measure key cardiovascular biomarkers, such as pulse wave velocity and arterial stiffness.
By enabling real-time screening of arterial elasticity and providing true beat-to-beat tracking of vascular health, QBS empowers clinicians with actionable data to make informed decisions. This approach enhances patient outcomes, supports early interventions, and helps prevent severe incidents—expanding accessibility to proactive cardiovascular care in both primary care and home settings.
TEAM 5: CoughSense
Project Mentors:
Henry Wei, MD, Head of Development Innovation, Regeneron
Gillian MacLochlainn PhD, Associate Director, Development Innovation, Regeneron
Project Summary
Respiratory diseases such as COPD, asthma, and lung cancer are among the leading causes of morbidity and mortality worldwide, impacting millions of patients annually. Accurate and continuous monitoring of cough frequency and severity is critical but remains challenging in standard clinical settings. Current approaches rely on patient self-reporting, which is often unreliable and burdensome. Addressing this gap could improve therapeutic outcomes, reduce healthcare costs, and advance medical research. This project proposes a mobile application for automated cough recognition and logging, tailored for iOS, to streamline data collection and empower both patients and providers with actionable insights. The application will be particularly beneficial in outpatient monitoring and clinical research settings. Apple’s cough recognition API provides a robust foundation. Coupled with Spezi for secure data handling and user interface design, the app will integrate seamlessly into existing clinical workflows. No previous prototype exists for this specific use case.